Chapter 3

How It Works: A Predictive Maintenance Example

Imagine that your company has well sites at different locations where you operate multiple pumps to extract oil and gas from the ground. The following example focuses on applying predictive maintenance to a digital twin asset.


Example Asset: Pump

Remember that a digital twin is an up-to-date representation of a real asset in operation.

An asset can be a:

Component of a system, such as the valve of a pump

Component of a system

System, the pump itself

System of systems

System of systems, such as a well site with multiple pumps

Digital Twins Predictive Maintenance Example Asset Positive Displace Pump

Positive displacement pump.

The asset is the pump in the following example. There are three well sites at different locations with multiple pumps running at each of the well sites.

Asset Pump Map

How does the digital twin model work?

You can create an up-to-date representation of the pump by building a model that gets updated with the incoming data from the pump—such as data transmitted from sensors and current operating conditions.

The digital twin model then represents the current state of the pump.

This image shows sensor measurements and operating conditions are sent from the pump to the model. The model takes these readings and outputs the current state of the pump.


Having a digital twin model of the pump provides several advantages

Equipment Downtime Reduction

Each pump contains expensive parts such as valves, seals, and plungers. You can to prevent failures by predicting them in advance, which, in turn, will help reduce downtime.

Inventory Management

You may also want to identify faults that develop and get insights into what parts may need repair or replacement. Doing so will also help you better manage your parts inventory.

Fleet Management, What-If Simulations, and Operational Planning

In the three well-site locations, all the pumps may have similar functionality. They might even be produced by the same manufacturer. But different operating conditions such as environmental temperature will affect how efficiently these pumps work.

You want to be able to monitor the whole fleet, simulate future scenarios, and make comparisons with the aim of increasing the overall efficiency of the fleet. This will help you with operational planning.

Digital Twins Predictive Maintenance having Pump Provides Several Advantages

Each well site has different average temperature operating conditions.